Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    from the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Benny
    0.44
    ล่า
    0.43
    kah
    0.42
    che
    0.41
    ोरा
    0.41
     exclusion
    0.40
     SAD
    0.40
    usion
    0.39
    ayah
    0.39
    ks
    0.39
    POSITIVE LOGITS
    their
    0.52
    embert
    0.52
    ..</
    0.50
     Revolt
    0.48
    ''}
    0.46
    itemName
    0.46
    ;
    0.45
     সকলকে
    0.44
     obecnie
    0.44
    swadian
    0.44
    Act Density 0.001%

    No Known Activations